Design of a Low-Cost Diffuse Optical Mammography System for Biomedical Image Processing in Breast Cancer Diagnosis.

Worldwide, breast cancer is the most common type of cancer that mainly affects women. Several diagnosis techniques based on optical instrumentation and image analysis have been developed, and these are commonly used in conjunction with conventional diagnostic devices such as mammographs, ultrasound, and magnetic resonance imaging of the breast. The cost of using these instruments is increasing, and developing countries, whose deaths indices due to breast cancer are high, cannot access conventional diagnostic methods and have even less access to newer techniques. Other studies, based on the analysis of images acquired by traditional methods, require high resolutions and knowledge of the origin of the captures in order to avoid errors. For this reason, the design of a low-cost diffuse optical mammography system for biomedical image processing in breast cancer diagnosis is presented. The system combines the acquisition of breast tissue photographs, diffuse optical reflectance (as a biophotonics technique), and the processing of digital images for the study and diagnosis of breast cancer. The system was developed in the form of a medical examination table with a 638 nm red-light source, using light-emitted diode technology (LED) and a low-cost web camera for the acquisition of breast tissue images. The system is automatic, and its control, through a graphical user interface (GUI), saves costs and allows for the subsequent analysis of images using a digital image-processing algorithm. The results obtained allow for the possibility of planning in vivo measurements. In addition, the acquisition of images every 30° around the breast tissue could be used in future research in order to perform a three-dimensional (3D) reconstruction and an analysis of the captures through deep learning techniques. These could be combined with virtual, augmented, or mixed reality environments to predict the position of tumors, increase the likelihood of a correct medical diagnosis, and develop a training system for specialists. Furthermore, the system allows for the possibility to develop analysis of optical characterization for new phantom studies in breast cancer diagnosis through bioimaging techniques.

Combined methods of optical spectroscopy and artificial intelligence in the assessment of experimentally induced non-alcoholic fatty liver.

BACKGROUND AND OBJECTIVE: Due to the existing prevalence of nonalcoholic fatty liver disease (NAFLD) and its relation to the epidemic of obesity in the general population, it is imperative to develop detection and evaluation methods of the early stages of the disease with improved efficacy over the current diagnostic approaches. We aimed to obtain an improved diagnosis, combining methods of optical spectroscopy -diffuse reflectance and fluorescence- with statistical data analysis applied to detect early stages of NAFLD. METHODS: Statistical analysis scheme based on quadratic discriminant analysis followed by canonical discriminant analysis were applied to the diffuse reflectance data combined with endogenous fluorescence spectral data excited at one of these wavelengths: 330, 365, 385, 405 or 415 nm. The statistical scheme was also applied to the combinations of fluorescence spectrum (405 nm) with each one of the other fluorescence spectra. Details of the developed software, including the application of machine learning algorithms to the combination of spectral data followed by classification statistical schemes, are discussed. RESULTS: Steatosis progression was differentiated with little classification error (≤1.3%) by using diffuse reflectance and endogenous fluorescence at different wavelengths. Similar results were obtained using fluorescence at 405 nm and one of the other fluorescence spectra (classification error ≤1.0%). Adding the corresponding areas under the curves to the above combinations of spectra diminished errors to 0.6% and 0.3% or less, respectively. The best results for the compounded reflectance-plus-fluorescence spectra were obtained with fluorescence spectra excited at 415 nm with a total classification error of 0.2%; for the combination of the 405nm-excited fluorescence spectrum with another fluorescence spectrum, the best results were achieved for 385 nm, for which total relative classification error amounted 0.4%. The consideration of the area under the spectral curves further improved both classifiers, reducing the error to 0.0% in both cases. CONCLUSION: Spectrometric techniques combined with statistical processing are a promising tool to improve steatosis classification through a label free approach. However, statistical schemes here applied, might result complex for the everyday medical practice, the designed software including machine learning algorithms is able to render automatic classification of samples according to their steatosis grade with low error.

Fluorescence spectroscopy on paraffin-preserved human liver samples to classify several grades of fibrosis.

Nowadays, it is well established that biopsy is the gold standard for medical diagnosis of liver disease; however, recent studies have shown numerous discrepancies in biopsy assessment, even when it is evaluated by senior pathologists. Fluorescence spectroscopy is a tool that has been of utility in the diagnosis of different diseases based on biopsy analysis. Thus, fluorescence study of liver samples with five different degrees of fibrosis is presented. Paraffin-preserved human liver tissue was provided on white plastic cassettes by the Hospital General de Mexico "Dr. Eduardo Liceaga". Specimens were diagnosed by two independent-senior pathologists in a double-blind test and classified into five different groups: F0, F1, F2, F3, and F4, according to the METAVIR scale for liver fibrosis. Fluorescence spectroscopy measurements were performed using three different excitation wavelengths: 385, 405, and 450 nm. Besides, diffuse reflectance spectroscopy (DRS) measurements were taken with white light to determine morphological changes in the tissue and to compare the results with medical diagnosis. The spectral analysis at excitation wavelengths of 385 nm and 405 nm showed poor correlation with medical diagnosis. Likewise, in order to discard all possible error-sources involved in the measurements, an exhaustive study was carried out; it included the determination of the fluorescence noise produced by paraffin, cassette, and the tissue itself. At 450 nm excitation wavelength, no fluorescence by the cassette was detected and noise-subtraction methods were not required, this allows a high correlation of hepatic fibrosis stages between pathological diagnosis and spectroscopic analysis. For this excitation wavelength, 89.87% correlation with DRS measurements and 82.00% with medical diagnosis were obtained. This work demonstrates that fluorescence spectroscopy using 450 nm excitation wavelength might work as a complementary tool to grade hepatic fibrosis in human liver specimens.

Fiber-optic pulseoximeter for local oxygen saturation determination using a Monte Carlo multi-layer model for calibration.

BACKGROUND AND OBJECTIVE: Local tissue oxygenation determines the relationship between the supply and the demand for oxygen by the tissue and it is an important indicator of the physiological or pathological condition of the tissue. Moreover, some therapeutic methods strongly depend on the oxygen content of the tissue. In photodynamic therapy, when molecular oxygen is present, the irradiation of the photosensitizer with light triggers the generation of reactive oxygen species that kill the target diseased cells within the treated tissue. To ensure the best possible therapy response, the tissue must be well oxygenated; hence, oxygen concentration measurement becomes a decisive factor. In this work, the design, construction and calibration of a module to locally measure the blood oxygen saturation in tissue is presented. METHODS: The system is built using a red (660-nm) and an infrared (940-nm) light emitting diodes as light sources, a photodiode as a detector, and a homemade handheld fiber optic-based reflectance pulse oximetry sensor. In addition, the developed sensor was modeled by means of multilayered Monte Carlo simulations, to study its behavior when used in different thickness and melanin content skin. RESULTS: From the simulation reflectance values, the oxygen saturation calibration curves considering different melanin concentrations and skin thicknesses were obtained for two different skin models, one comprising three skin layers and the second, assuming seven different layers for the skin. A comparison of the performances of the developed pulse oximeter sensor with a commercial one is also presented. CONCLUSIONS: A new pulseoximeter for the measurement of local oxygenation in tissue was developed. Its calibration strongly depends on the site of measurement due to the influence of tissue thickness, vascularization, and melanin content. A three-layer skin model is proved to be suitable for the calibration of the pulseoximeter in thin and medium thickness skin.

Study of Methionine Choline Deficient Diet-Induced Steatosis in Mice Using Endogenous Fluorescence Spectroscopy.

Non-alcoholic fatty liver disease is a highly prevalent condition worldwide that increases the risk to develop liver fibrosis, cirrhosis, and hepatocellular carcinoma. Thus, it is imperative to develop novel diagnostic tools that together with liver biopsy help to differentiate mild and advanced degrees of steatosis. Ex-vivo liver samples were collected from mice fed a methionine-choline deficient diet for two or eight weeks, and from a control group. The degree of hepatic steatosis was histologically evaluated, and fat content was assessed by Oil-Red O staining. On the other hand, fluorescence spectroscopy was used for the assessment of the steatosis progression. Fluorescence spectra were recorded at excitation wavelengths of 330, 365, 385, 405, and 415 nm by establishing surface contact of the fiber optic probe with the liver specimens. A multi-variate statistical approach based on principal component analysis followed by quadratic discriminant analysis was applied to spectral data to obtain classifiers able to distinguish mild and moderate stages of steatosis at the different excitation wavelengths. Receiver Operating Characteristic (ROC) curves were computed to compare classifier's performances for each one of the five excitation wavelengths and steatosis stages. Optimal sensitivity and specificity were calculated from the corresponding ROC curves using the Youden index. Intensity in the endogenous fluorescence spectra at the given wavelengths progressively increased according to the time of exposure to diet. The area under the curve of the spectra was able to discriminate control liver samples from those with steatosis and differentiate among the time of exposure to the diet for most of the used excitation wavelengths. High specificities and sensitivities were obtained for every case; however, fluorescence spectra obtained by exciting with 405 nm yielded the best results distinguishing between the mentioned classes with a total classification error of 1.5% and optimal sensitivities and specificities better than 98.6% and 99.3%, respectively.